[GH-ISSUE #11199] Request for Support of AMD Ryzen AI Platform NPU #53891

New Issue

GiteaMirror · 2026-04-29T04:55:13-05:00

GiteaMirror commented

2026-04-29 04:55:13 -05:00

Originally created by @netqer on GitHub (Jun 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11199

Dear ollama team,

I'm writing to submit a feature request: please consider adding official support for the AMD Ryzen AI platform NPU .

Currently, AMD has provided an initial implementation in their open-source project:
🔗 https://github.com/amd/RyzenAI-SW/tree/1.2.0/example/transformers/ext/llama.cpp

However, based on community feedback, this implementation may still have room for improvement in terms of performance and usability. Integrating this functionality into the official llama.cpp repository could help improve cross-platform compatibility.

It's also worth noting that different platforms support varying quantization precisions:

STX (e.g., HX370) supports both W8A16 and W4ABF16
PHX (e.g., 7840HS), HPT (e.g., 8845HS) support W4ABF16, but NOT support W8A16
For more details, please refer to:
🔗 https://github.com/amd/RyzenAI-SW/blob/1.2.0/example/transformers/models/llm/docs/README.md

Thank you for your hard work and contributions! We look forward to better support for Ryzen AI NPUs in the future.

Originally created by @netqer on GitHub (Jun 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11199 Dear ollama team, I'm writing to submit a feature request: please consider adding official support for the AMD Ryzen AI platform NPU . Currently, AMD has provided an initial implementation in their open-source project: 🔗 https://github.com/amd/RyzenAI-SW/tree/1.2.0/example/transformers/ext/llama.cpp However, based on community feedback, this implementation may still have room for improvement in terms of performance and usability. Integrating this functionality into the official llama.cpp repository could help improve cross-platform compatibility. It's also worth noting that different platforms support varying quantization precisions: STX (e.g., HX370) supports both W8A16 and W4ABF16 PHX (e.g., 7840HS), HPT (e.g., 8845HS) support W4ABF16, but NOT support W8A16 For more details, please refer to: 🔗 https://github.com/amd/RyzenAI-SW/blob/1.2.0/example/transformers/models/llm/docs/README.md Thank you for your hard work and contributions! We look forward to better support for Ryzen AI NPUs in the future.

GiteaMirror added the feature request label 2026-04-29 04:55:13 -05:00

GiteaMirror commented

2026-04-29 04:55:14 -05:00

@jmorille commented on GitHub (Jun 25, 2025):

+1 Please add support

@jmorille commented on GitHub (Jun 25, 2025): +1 Please add support

GiteaMirror commented

2026-04-29 04:55:15 -05:00

@rick-github commented on GitHub (Jun 25, 2025):

#5186

@rick-github commented on GitHub (Jun 25, 2025): #5186

GiteaMirror commented

2026-04-29 04:55:15 -05:00

@netqer commented on GitHub (Jun 26, 2025):

#5186

We noticed that there has been considerable discussion around NPU support (e.g, #5186), but it turns out that AMD has already provided a preliminary implementation based on llama.cpp. If the ollama team is open to integrating these existing resources, we believe this could significantly accelerate the development of native Ryzen AI platform NPU support.

Moreover, there are hardware capability differences across the different NPU platforms:

PHX (e.g., 7840HS) and HPT (e.g., 8845HS) mainly support W4ABF16 quantization
STX (e.g., HX370) additionally supports W8A16
These differences require careful handling during model loading and inference. Fortunately, AMD’s documentation and code provide necessary guidance for such adaptations.

Notably, AMD has also exposed low-level operator implementations for the NPU in the following directory:
🔗 https://github.com/amd/RyzenAI-SW/tree/1.2.0/example/transformers/ops

This codebase can serve as a crucial reference for integrating the NPU backend into llama.cpp, helping developers build a performant and robust solution more efficiently.

We hope the ollama team can consider including Ryzen AI NPU support in the project's roadmap. we also willing to assist with testing or even contribute to the development if needed.

@netqer commented on GitHub (Jun 26, 2025): > [#5186](https://github.com/ollama/ollama/issues/5186) We noticed that there has been considerable discussion around NPU support (e.g, #5186), but it turns out that AMD has already provided a preliminary implementation based on llama.cpp. If the ollama team is open to integrating these existing resources, we believe this could significantly accelerate the development of native Ryzen AI platform NPU support. Moreover, there are hardware capability differences across the different NPU platforms: PHX (e.g., 7840HS) and HPT (e.g., 8845HS) mainly support W4ABF16 quantization STX (e.g., HX370) additionally supports W8A16 These differences require careful handling during model loading and inference. Fortunately, AMD’s documentation and code provide necessary guidance for such adaptations. Notably, AMD has also exposed low-level operator implementations for the NPU in the following directory: 🔗 https://github.com/amd/RyzenAI-SW/tree/1.2.0/example/transformers/ops This codebase can serve as a crucial reference for integrating the NPU backend into llama.cpp, helping developers build a performant and robust solution more efficiently. We hope the ollama team can consider including Ryzen AI NPU support in the project's roadmap. we also willing to assist with testing or even contribute to the development if needed.

GiteaMirror commented

2026-04-29 04:55:15 -05:00

@aibotza commented on GitHub (Jul 1, 2025):

+1 Please add support for NPU

@aibotza commented on GitHub (Jul 1, 2025): +1 Please add support for NPU

GiteaMirror commented

2026-04-29 04:55:16 -05:00

@nedzad-winter commented on GitHub (Jul 2, 2025):

+1 Please

@nedzad-winter commented on GitHub (Jul 2, 2025): +1 Please

GiteaMirror commented

2026-04-29 04:55:16 -05:00

@jamesalster commented on GitHub (Jul 2, 2025):

Another +1, please!

@jamesalster commented on GitHub (Jul 2, 2025): Another +1, please!

GiteaMirror commented

2026-04-29 04:55:17 -05:00

@mlaihk commented on GitHub (Jul 4, 2025):

+1 Please!

@mlaihk commented on GitHub (Jul 4, 2025): +1 Please!

GiteaMirror commented

2026-04-29 04:55:17 -05:00

@TypicalZedF commented on GitHub (Jul 4, 2025):

+1 To this aswell. Id like to utilize the hardware on my computer with a 100% local AI

@TypicalZedF commented on GitHub (Jul 4, 2025): +1 To this aswell. Id like to utilize the hardware on my computer with a 100% local AI

GiteaMirror commented

2026-04-29 04:55:17 -05:00

@Alex18gr commented on GitHub (Jul 7, 2025):

+1 pleaseee

@Alex18gr commented on GitHub (Jul 7, 2025): +1 pleaseee

GiteaMirror commented

2026-04-29 04:55:18 -05:00

@jmorille commented on GitHub (Jul 8, 2025):

The integration of an AMD Ryzen AI NPU proves to be significantly more affordable than a comparable Nvidia GPU configuration, while offering a unified memory architecture shared with the CPU of up to 128 GB.

In a Home Lab context, this is particularly compelling because it enables running 70b LLMs locally without resorting to an overpriced high-end Nvidia graphics card to achieve equivalent VRAM capacity

@jmorille commented on GitHub (Jul 8, 2025): The integration of an AMD Ryzen AI NPU proves to be significantly more affordable than a comparable Nvidia GPU configuration, while offering a unified memory architecture shared with the CPU of up to 128 GB. In a Home Lab context, this is particularly compelling because it enables running 70b LLMs locally without resorting to an overpriced high-end Nvidia graphics card to achieve equivalent VRAM capacity

GiteaMirror commented

2026-04-29 04:55:18 -05:00

@leander19961 commented on GitHub (Jul 11, 2025):

+1 Please

@leander19961 commented on GitHub (Jul 11, 2025): +1 Please

GiteaMirror commented

2026-04-29 04:55:18 -05:00

@xiongyw commented on GitHub (Jul 12, 2025):

+1 please!

@xiongyw commented on GitHub (Jul 12, 2025): +1 please!

GiteaMirror commented

2026-04-29 04:55:20 -05:00

@emilianionascu commented on GitHub (Jul 14, 2025):

+1 😄

@emilianionascu commented on GitHub (Jul 14, 2025): +1 😄

GiteaMirror commented

2026-04-29 04:55:21 -05:00

@rammanokar-plateron commented on GitHub (Jul 16, 2025):

+1

@rammanokar-plateron commented on GitHub (Jul 16, 2025): +1

GiteaMirror commented

2026-04-29 04:55:22 -05:00

@webprofusion-chrisc commented on GitHub (Jul 18, 2025):

For background, there is an increasing proliferation of mini-PCs (and larger ones) which have the AMD NPU available, but sadly these sit at 0% resource utilization during even the toughest ollama tasks. It would be great to light these up with work to do!

@webprofusion-chrisc commented on GitHub (Jul 18, 2025): For background, there is an increasing proliferation of mini-PCs (and larger ones) which have the AMD NPU available, but sadly these sit at 0% resource utilization during even the toughest ollama tasks. It would be great to light these up with work to do!

GiteaMirror commented

2026-04-29 04:55:22 -05:00

@kazami308 commented on GitHub (Jul 20, 2025):

+1

@kazami308 commented on GitHub (Jul 20, 2025): +1

GiteaMirror commented

2026-04-29 04:55:22 -05:00

@ignamartinoli commented on GitHub (Jul 21, 2025):

+1

@ignamartinoli commented on GitHub (Jul 21, 2025): +1

GiteaMirror commented

2026-04-29 04:55:23 -05:00

@bartschneider commented on GitHub (Jul 24, 2025):

+1

@bartschneider commented on GitHub (Jul 24, 2025): +1

GiteaMirror commented

2026-04-29 04:55:23 -05:00

@4nd1syntz commented on GitHub (Jul 26, 2025):

+1

@4nd1syntz commented on GitHub (Jul 26, 2025): +1

GiteaMirror commented

2026-04-29 04:55:24 -05:00

@padthaitofuhot commented on GitHub (Jul 27, 2025):

+1

@padthaitofuhot commented on GitHub (Jul 27, 2025): +1

GiteaMirror commented

2026-04-29 04:55:24 -05:00

@Jynx commented on GitHub (Jul 28, 2025):

+1

@Jynx commented on GitHub (Jul 28, 2025): +1

GiteaMirror commented

2026-04-29 04:55:25 -05:00

@TesaTesa commented on GitHub (Jul 30, 2025):

+1

@TesaTesa commented on GitHub (Jul 30, 2025): +1

GiteaMirror commented

2026-04-29 04:55:25 -05:00

@pramodhrachuri commented on GitHub (Jul 30, 2025):

+1

@pramodhrachuri commented on GitHub (Jul 30, 2025): +1

GiteaMirror commented

2026-04-29 04:55:26 -05:00

@rafaelfaustini commented on GitHub (Jul 31, 2025):

+1

@rafaelfaustini commented on GitHub (Jul 31, 2025): +1

GiteaMirror commented

2026-04-29 04:55:27 -05:00

@dr3dr3 commented on GitHub (Aug 3, 2025):

+1

@dr3dr3 commented on GitHub (Aug 3, 2025): +1

GiteaMirror commented

2026-04-29 04:55:27 -05:00

@geethangreets commented on GitHub (Aug 6, 2025):

+1

@geethangreets commented on GitHub (Aug 6, 2025): +1

GiteaMirror commented

2026-04-29 04:55:28 -05:00

@KeithBronstrup commented on GitHub (Aug 6, 2025):

+1

@KeithBronstrup commented on GitHub (Aug 6, 2025): +1

GiteaMirror commented

2026-04-29 04:55:29 -05:00

@lizer2014 commented on GitHub (Aug 8, 2025):

+10086

@lizer2014 commented on GitHub (Aug 8, 2025): +10086

GiteaMirror commented

2026-04-29 04:55:29 -05:00

@UN-9BOT commented on GitHub (Aug 8, 2025):

+1

@UN-9BOT commented on GitHub (Aug 8, 2025): +1

GiteaMirror commented

2026-04-29 04:55:29 -05:00

@arhe1on commented on GitHub (Aug 12, 2025):

+1

@arhe1on commented on GitHub (Aug 12, 2025): +1

GiteaMirror commented

2026-04-29 04:55:30 -05:00

@theCalcaholic commented on GitHub (Aug 14, 2025):

+1

While I'm also very much hoping for the implementation of AMD NPU support in ollama, I'd ask you to please refrain from adding messages like this which do not contribute to a solution.

You can instead use emoji reactions (e.g. 👍) to show that you want this feature.

Thank you :)

@theCalcaholic commented on GitHub (Aug 14, 2025): > +1 While I'm also very much hoping for the implementation of AMD NPU support in ollama, I'd ask you to please refrain from adding messages like this which do not contribute to a solution. You can instead use emoji reactions (e.g. :+1:) to show that you want this feature. Thank you :)

GiteaMirror commented

2026-04-29 04:55:30 -05:00

@amxstudiohub commented on GitHub (Aug 14, 2025):

+1

@amxstudiohub commented on GitHub (Aug 14, 2025): +1

GiteaMirror commented

2026-04-29 04:55:31 -05:00

@ignamartinoli commented on GitHub (Aug 14, 2025):

@amxstudiohub based

@ignamartinoli commented on GitHub (Aug 14, 2025): @amxstudiohub based

GiteaMirror commented

2026-04-29 04:55:33 -05:00

@akulmambetov commented on GitHub (Aug 26, 2025):

+1

@akulmambetov commented on GitHub (Aug 26, 2025): +1

GiteaMirror commented

2026-04-29 04:55:33 -05:00

@Edu171002 commented on GitHub (Sep 18, 2025):

+1

@Edu171002 commented on GitHub (Sep 18, 2025): +1

GiteaMirror commented

2026-04-29 04:55:34 -05:00

@rstein85 commented on GitHub (Sep 30, 2025):

+1

@rstein85 commented on GitHub (Sep 30, 2025): +1

GiteaMirror commented

2026-04-29 04:55:34 -05:00

@Ragua1 commented on GitHub (Oct 2, 2025):

+1

@Ragua1 commented on GitHub (Oct 2, 2025): +1

GiteaMirror commented

2026-04-29 04:55:34 -05:00

@Tim-Gabrikowski commented on GitHub (Oct 20, 2025):

+1

@Tim-Gabrikowski commented on GitHub (Oct 20, 2025): +1

GiteaMirror commented

2026-04-29 04:55:35 -05:00

@aethersis commented on GitHub (Oct 21, 2025):

+1

@aethersis commented on GitHub (Oct 21, 2025): +1

GiteaMirror commented

2026-04-29 04:55:35 -05:00

@NinjaCats commented on GitHub (Oct 23, 2025):

+1😄

@NinjaCats commented on GitHub (Oct 23, 2025): +1😄

GiteaMirror commented

2026-04-29 04:55:35 -05:00

@Joeeey0219 commented on GitHub (Oct 23, 2025):

+1

@Joeeey0219 commented on GitHub (Oct 23, 2025): +1

GiteaMirror commented

2026-04-29 04:55:35 -05:00

@mistrjirka commented on GitHub (Oct 23, 2025):

For anyone wondering why the support is not there and probably won't be for some time is that AMD hard s*cks at supporting the NPUs (amazing mentality of investing billions into hw but having no interesting software support). There is very little documentation and sdk that actually work on all the OS llama.cpp supports. The AMD sdk works currently only on windows. If you want to use the NPU on windows you can try Lemonade server.

@mistrjirka commented on GitHub (Oct 23, 2025): For anyone wondering why the support is not there and probably won't be for some time is that AMD hard s*cks at supporting the NPUs (amazing mentality of investing billions into hw but having no interesting software support). There is very little documentation and sdk that actually work on all the OS llama.cpp supports. The AMD sdk works currently only on windows. If you want to use the NPU on windows you can try Lemonade server.

GiteaMirror commented

2026-04-29 04:55:36 -05:00

@ziouf commented on GitHub (Oct 30, 2025):

NPU seem to be supported on Linux as stated by Th3raid0r in a comment on lemonade-sdk Discord chanel

need kernel 6.14 for the driver to be built-in
need the shim in the repo driver https://github.com/amd/xdna-driver
need latest build of TheROCK https://github.com/ROCm/TheRock
Officials toolkits known are https://github.com/Xilinx/XRT, https://github.com/Xilinx/mlir-aie

NPU is detected

$ lspci | grep -i neural

c4:00.1 Signal processing controller: Advanced Micro Devices, Inc. [AMD] Strix/Krackan/Strix Halo Neural Processing Unit (rev 11)

The driver is loaded

$ lsmod | grep xdna

amdxdna               176128  0
gpu_sched              69632  2 amdxdna,amdgpu

rocminfo sees it

$ rocminfo | grep aie2 -A 4

  Name:                    aie2
  Uuid:                    AIE-XX
  Marketing Name:          AIE-ML
  Vendor Name:             AMD
  Feature:                 AGENT_DISPATCH

we can afford to be a little optimistic

edit:
https://www.phoronix.com/news/AMD-Ryzen-AI-XDNA-NPU3A

@ziouf commented on GitHub (Oct 30, 2025): NPU seem to be supported on Linux as stated by Th3raid0r in a comment on lemonade-sdk Discord chanel - need kernel 6.14 for the driver to be built-in - need the shim in the repo driver https://github.com/amd/xdna-driver - need latest build of TheROCK https://github.com/ROCm/TheRock - Officials toolkits known are https://github.com/Xilinx/XRT, https://github.com/Xilinx/mlir-aie NPU is detected ``` $ lspci | grep -i neural c4:00.1 Signal processing controller: Advanced Micro Devices, Inc. [AMD] Strix/Krackan/Strix Halo Neural Processing Unit (rev 11) ``` The driver is loaded ``` $ lsmod | grep xdna amdxdna 176128 0 gpu_sched 69632 2 amdxdna,amdgpu ``` rocminfo sees it ``` $ rocminfo | grep aie2 -A 4 Name: aie2 Uuid: AIE-XX Marketing Name: AIE-ML Vendor Name: AMD Feature: AGENT_DISPATCH ``` we can afford to be a little optimistic edit: https://www.phoronix.com/news/AMD-Ryzen-AI-XDNA-NPU3A

GiteaMirror commented

2026-04-29 04:55:36 -05:00

@kenneth-ge commented on GitHub (Jan 20, 2026):

+1

@kenneth-ge commented on GitHub (Jan 20, 2026): +1

GiteaMirror commented

2026-04-29 04:55:36 -05:00

@mistrjirka commented on GitHub (Jan 20, 2026):

NPU seem to be supported on Linux as stated by Th3raid0r in a comment on lemonade-sdk Discord chanel

* need kernel 6.14 for the driver to be built-in

* need the shim in the repo driver https://github.com/amd/xdna-driver

* need latest build of TheROCK https://github.com/ROCm/TheRock

* Officials toolkits known are https://github.com/Xilinx/XRT, https://github.com/Xilinx/mlir-aie

NPU is detected

$ lspci | grep -i neural

c4:00.1 Signal processing controller: Advanced Micro Devices, Inc. [AMD] Strix/Krackan/Strix Halo Neural Processing Unit (rev 11)

The driver is loaded

$ lsmod | grep xdna

amdxdna               176128  0
gpu_sched              69632  2 amdxdna,amdgpu

rocminfo sees it

$ rocminfo | grep aie2 -A 4

  Name:                    aie2
  Uuid:                    AIE-XX
  Marketing Name:          AIE-ML
  Vendor Name:             AMD
  Feature:                 AGENT_DISPATCH

we can afford to be a little optimistic

edit: https://www.phoronix.com/news/AMD-Ryzen-AI-XDNA-NPU3A

I tried running some demos on the NPU, sadly the current XRT that actually supports XDNA2 is in closed beta and to get access to it you need to "sign" an NDA and be part of some larger company. I think that it would be possible for someone from here to get the access, I tried it personally but could not.

@mistrjirka commented on GitHub (Jan 20, 2026): > NPU seem to be supported on Linux as stated by Th3raid0r in a comment on lemonade-sdk Discord chanel > > * need kernel 6.14 for the driver to be built-in > > * need the shim in the repo driver https://github.com/amd/xdna-driver > > * need latest build of TheROCK https://github.com/ROCm/TheRock > > * Officials toolkits known are https://github.com/Xilinx/XRT, https://github.com/Xilinx/mlir-aie > > > NPU is detected > > ``` > $ lspci | grep -i neural > > c4:00.1 Signal processing controller: Advanced Micro Devices, Inc. [AMD] Strix/Krackan/Strix Halo Neural Processing Unit (rev 11) > ``` > > The driver is loaded > > ``` > $ lsmod | grep xdna > > amdxdna 176128 0 > gpu_sched 69632 2 amdxdna,amdgpu > ``` > > rocminfo sees it > > ``` > $ rocminfo | grep aie2 -A 4 > > Name: aie2 > Uuid: AIE-XX > Marketing Name: AIE-ML > Vendor Name: AMD > Feature: AGENT_DISPATCH > ``` > > we can afford to be a little optimistic > > edit: https://www.phoronix.com/news/AMD-Ryzen-AI-XDNA-NPU3A I tried running some demos on the NPU, sadly the current XRT that actually supports XDNA2 is in closed beta and to get access to it you need to "sign" an NDA and be part of some larger company. I think that it would be possible for someone from here to get the access, I tried it personally but could not.

GiteaMirror commented

2026-04-29 04:55:37 -05:00

@ivpoov commented on GitHub (Feb 7, 2026):

+1

@ivpoov commented on GitHub (Feb 7, 2026): +1

GiteaMirror commented

2026-04-29 04:55:37 -05:00

@rladinger commented on GitHub (Feb 14, 2026):

+1

@rladinger commented on GitHub (Feb 14, 2026): +1

GiteaMirror commented

2026-04-29 04:55:37 -05:00

@ClementGayet commented on GitHub (Feb 16, 2026):

+1

@ClementGayet commented on GitHub (Feb 16, 2026): +1

GiteaMirror commented

2026-04-29 04:55:37 -05:00

@TSJasonH commented on GitHub (Mar 20, 2026):

+1

@TSJasonH commented on GitHub (Mar 20, 2026): +1

GiteaMirror commented

2026-04-29 04:55:37 -05:00

@PCAssistSoftware commented on GitHub (Mar 24, 2026):

+1

@PCAssistSoftware commented on GitHub (Mar 24, 2026): +1

GiteaMirror commented

2026-04-29 04:55:38 -05:00

@d4rkr0n1n commented on GitHub (Apr 3, 2026):

+1

@d4rkr0n1n commented on GitHub (Apr 3, 2026): +1

GiteaMirror commented

2026-04-29 04:55:38 -05:00

@xiongsongsong commented on GitHub (Apr 4, 2026):

+1

@xiongsongsong commented on GitHub (Apr 4, 2026): +1

GiteaMirror commented

2026-04-29 04:55:38 -05:00

@Faisal-Alessa commented on GitHub (Apr 4, 2026):

+1

@Faisal-Alessa commented on GitHub (Apr 4, 2026): +1

GiteaMirror commented

2026-04-29 04:55:39 -05:00

@Laotu77 commented on GitHub (Apr 14, 2026):

+1

@Laotu77 commented on GitHub (Apr 14, 2026): +1

GiteaMirror commented

2026-04-29 04:55:39 -05:00

@pmssantos commented on GitHub (Apr 17, 2026):

+1

@pmssantos commented on GitHub (Apr 17, 2026): +1

GiteaMirror commented

2026-04-29 04:55:39 -05:00

@Syphdias commented on GitHub (Apr 18, 2026):

Please lock this issue or limit to maintainers to stop people from commenting "+1" instead of reacting to the issue because this triggers notifications to ~50 watchers. Thank you :)

@Syphdias commented on GitHub (Apr 18, 2026): Please lock this issue or limit to maintainers to stop people from commenting "+1" instead of reacting to the issue because this triggers notifications to ~50 watchers. Thank you :)

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#53891